Mistral Small 22B FP16

Popular Ollama model family: Mistral Small. Caveat: Estimated values are placeholders unless marked measured..

Hardware Snapshot

Family Mistral Small
Scenario chat
License scope closed-weight
Quantization FP16
VRAM minimum 30GB
VRAM optimal 42GB
Best local GPU RTX 6000 Ada 48GB
Cloud fallback A100 80GB
Updated 2026-02-24
Data status Verified by Real Hardware
Ollama source Library reference (verified: 2026-02-24)
Ollama tag mistral-small:22b
Category chat

Benchmark Anchors

Hardware Expected tok/s
RTX 3090 24GB 6.1
RTX 4090 24GB 8.2
A100 80GB 14.6

Real Hardware Benchmark (RTX 3090)

Tokens/s 16.674
Latency 5609 ms
Prompt tokens 29
Eval tokens 84
Test time 2026-04-01T11:53:50Z
GPU model NVIDIA GeForce RTX 3090

Verified by real hardware.

View raw nvidia-smi snapshot

Performance Curve

Reference anchors are baseline estimates. Measured RTX 3090 data is overlaid when available.

Best Hardware for Mistral Small 22B FP16

Local vs Cloud Cost Hint

Mode 40h / month 120h / month
Local power only (3090 baseline) $2.24 $6.72
A100 80GB $78 $234
ollama run mistral-small:22b More chat models More 30b-34b models Benchmark changelog Submit your test result Run on RunPod Try Vast.ai

We may earn a commission if you click links on this page.